ALBERT

Description: Background A promising direction in the analysis of gene expression focuses on the changes in expression of specific predefined sets of genes that are known in advance to be related (e.g., genes coding for proteins involved in cellular pathways or complexes). Such an analysis can reveal features that are not easily visible from the variations in the individual genes and can lead to a picture of expression that is more biologically transparent and accessible to interpretation. In this article, we present a new method of this kind that operates by quantifying the level of 'activity' of each pathway in different samples. The activity levels, which are derived from singular value decompositions, form the basis for statistical comparisons and other applications. Results We demonstrate our approach using expression data from a study of type 2 diabetes and another of the influence of cigarette smoke on gene expression in airway epithelia. A number of interesting pathways are identified in comparisons between smokers and non-smokers including ones related to nicotine metabolism, mucus production, and glutathione metabolism. A comparison with results from the related approach, 'gene-set enrichment analysis', is also provided. Conclusion Our method offers a flexible basis for identifying differentially expressed pathways from gene expression data. The results of a pathway-based analysis can be complementary to those obtained from one more focused on individual genes. A web program PLAGE (Pathway Level Analysis of Gene Expression) for performing the kinds of analyses described here is accessible at http://dulci.biostat.duke.edu/pathways.

Description: Background Establishment of peptide binding to Major Histocompatibility Complex class I (MHCI) is a crucial step in the development of subunit vaccines and prediction of such binding could greatly reduce costs and accelerate the experimental process of identifying immunogenic peptides. Many methods have been applied to the prediction of peptide-MHCI binding, with some achieving outstanding performance. Because of the experimental methods used to measure binding or affinity between peptides and MHCI molecules, however, available datasets are enriched for nonbinders, and thus highly unbalanced. Although there is no consensus on the ideal class distribution for training sets, extremely unbalanced datasets can be detrimental to the performance of prediction algorithms. Results We have developed a decision-theoretic framework to construct cost-sensitive trees to predict peptide-MHCI binding and have used them to 1) Assess the impact of the training data's class distribution on classifier accuracy, and 2) Compare resampling and cost-sensitive methods as approaches to compensate for training data imbalance. Our results confirm that highly unbalanced training sets can reduce the accuracy of classifier predictions and show that, in the peptide-MHCI binding context, resampling methods do not improve the classifier performance. In contrast, cost-sensitive methods significantly improve accuracy of decision trees. Finally, we propose the use of a training scheme that, when the training set is enriched for nonbinders, consistently improves the overall classifier accuracy compared to cost-insensitive classifiers and, in particular, increases the sensitivity of the classifiers. This method minimizes the expected classification cost for large datasets. Conclusion Our method consistently improves the performance of decision trees in predicting peptide-MHC class I binding by using cost-balancing techniques to compensate for the imbalance in the training dataset.

Description: Background In testing for differential gene expression involving multiple serial analysis of gene expression (SAGE) libraries, it is critical to account for both between and within library variation. Several methods have been proposed, including the t test, t w test, and an overdispersed logistic regression approach. The merits of these tests, however, have not been fully evaluated. Questions still remain on whether further improvements can be made. Results In this article, we introduce an overdispersed log-linear model approach to analyzing SAGE; we evaluate and compare its performance with three other tests: the two-sample t test, t w test and another based on overdispersed logistic linear regression. Analysis of simulated and real datasets show that both the log-linear and logistic overdispersion methods generally perform better than the t and t w tests; the log-linear method is further found to have better performance than the logistic method, showing equal or higher statistical power over a range of parameter values and with different data distributions. Conclusion Overdispersed log-linear models provide an attractive and reliable framework for analyzing SAGE experiments involving multiple libraries. For convenience, the implementation of this method is available through a user-friendly web-interface available at http://www.cbcb.duke.edu/sage.